Skip to content
conftrace_
2025 CoRL CoRL 2025

HALO : Human Preference Aligned Offline Reward Learning for Robot Navigation

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Reinforcement Learning and Robotics

Authors

Gershom Seneviratne, Jianyu An, Jian Yuan, Sahire Ellahy, Kasun Weerakoon, Mohamed Bashir Elnoor, Jonathan Deepak Kannan, Amogha Thalihalla Sunil, Dinesh Manocha

Topics

Reinforcement Learning > Methods > Offline RL Robotics > Capabilities > Human-Robot Interaction Robotics > Capabilities > Navigation

Keywords

human preference score expert trajectories boltzmann probability distribution egocentric camera feed offline reward learning plackett-luce loss
Download PDF